Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2866 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.0977. Min Range: -2.0977
Max Act: 2.0977. Min Act: -0.1700
Data Index: 5392553 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0977. Min Range: -2.0977
Max Act: 2.0641. Min Act: -0.1700
Data Index: 7839034 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0977. Min Range: -2.0977
Max Act: 2.0473. Min Act: -0.1700
Data Index: 7839029 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0977. Min Range: -2.0977
Max Act: 2.0473. Min Act: -0.1700
Data Index: 7121727 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0977. Min Range: -2.0977
Max Act: 2.0305. Min Act: -0.1700
Data Index: 8495317 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0977. Min Range: -2.0977
Max Act: 1.9967. Min Act: -0.1699
Data Index: 47048 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0977. Min Range: -2.0977
Max Act: 1.9798. Min Act: -0.1700
Data Index: 5265654 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0977. Min Range: -2.0977
Max Act: 1.9544. Min Act: -0.1700
Data Index: 8300231 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0977. Min Range: -2.0977
Max Act: 1.9628. Min Act: -0.1700
Data Index: 1419169 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0977. Min Range: -2.0977
Max Act: 1.9628. Min Act: -0.1700
Data Index: 3622037 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0977. Min Range: -2.0977
Max Act: 1.9459. Min Act: -0.1700
Data Index: 8607516 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0977. Min Range: -2.0977
Max Act: 1.9289. Min Act: -0.1700
Data Index: 2947030 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0977. Min Range: -2.0977
Max Act: 1.9374. Min Act: -0.1700
Data Index: 4468004 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0977. Min Range: -2.0977
Max Act: 1.9289. Min Act: -0.1700
Data Index: 5622289 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0977. Min Range: -2.0977
Max Act: 1.9289. Min Act: -0.1700
Data Index: 1325886 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0977. Min Range: -2.0977
Max Act: 1.9204. Min Act: -0.1700
Data Index: 5182702 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0977. Min Range: -2.0977
Max Act: 1.9118. Min Act: -0.1700
Data Index: 8501149 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0977. Min Range: -2.0977
Max Act: 1.9204. Min Act: -0.1700
Data Index: 8257028 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0977. Min Range: -2.0977
Max Act: 1.9204. Min Act: -0.1700
Data Index: 5891228 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0977. Min Range: -2.0977
Max Act: 1.9204. Min Act: -0.1700
Data Index: 6534527 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19